Skip to main content
POST
/
producer
/
audios
音频生成
curl --request POST \
  --url https://api.mountsea.ai/producer/audios \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "action": "create_music",
  "soundPrompt": "driving energetic beat, rapid rhythm, high BPM",
  "lyrics": "[Verse 1]\nI've been running in circles...\n\n[Chorus]\nI keep coming back to you...",
  "title": "Back to You",
  "model": "Lyria 3 Pro",
  "seed": 877369,
  "makeInstrumental": false,
  "imageUrl": "https://example.com/cover.jpg"
}
EOF
{
  "taskId": "<string>"
}
Generate music using Google DeepMind’s Lyria 3 Pro model. Provide a sound prompt describing the desired style and/or lyrics to create original tracks.
This is an async task. The response contains a taskId — use Get Task Status to poll for the generated audio.

​
Tips

  • Sound Prompt: Describe the musical style, mood, instruments, and tempo (e.g., "emotional pop with gentle piano, warm synths, and a catchy beat")
  • Lyrics: Use section tags like [Verse], [Chorus], [Bridge] for structured output
  • Image-Guided: Provide an imageUrl to let the model infer mood and style from an image
  • Instrumental: Set makeInstrumental: true to generate without vocals
  • Reproducibility: Use seed for deterministic generation — same seed + same parameters = same output

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
action
enum<string>
required

Action type to perform

Available options:
create_music
Example:

"create_music"

​
soundPrompt
string

Sound/style prompt describing the desired music style

Example:

"driving energetic beat, rapid rhythm, high BPM"

​
lyrics
string

Lyrics content with section tags like [Verse], [Chorus], etc. For create_music: either soundPrompt or lyrics should be provided. Set makeInstrumental=true to ignore lyrics.

Example:

"[Verse 1]\nI've been running in circles...\n\n[Chorus]\nI keep coming back to you..."

​
title
string

Song title (max 80 characters)

Maximum string length: 80
Example:

"Back to You"

​
model
enum<string>

Music generation model (currently only Lyria 3 Pro)

Available options:
Lyria 3 Pro
Example:

"Lyria 3 Pro"

​
seed
number

Random seed for reproducible generation

Example:

877369

​
makeInstrumental
boolean

Generate instrumental only (ignores lyrics). Default: false

Example:

false

​
imageUrl
string

Image URL for image-guided generation (will be uploaded automatically)

Example:

"https://example.com/cover.jpg"

Response

任务创建成功

​
taskId
string
required

任务 ID，用于后续查询结果